Skip to main content
The app has no Analytics section and no /analytics/* pages. Your numbers are read in two places: the Scoreboard, the first tab of the right panel in a thread and a page of its own at /scoreboard with its analysis views (Overview, Topics, Markets and the prompt Grid), the metric drill-down at /scoreboard/metrics/<metric> and engine detail at /scoreboard/engines/<engine>, and the analysis cards the agent draws when you ask in a chat. Your assistant and your code read the same data over MCP and the REST API. On every one of them, a dash and a zero mean different things:
A dash means not measured: no answer was read for it. A 0 means we read the answers and the count was zero.

The verdict words

Every shipped change is judged in one of four words, with the reason for the verdict in one line. The verdict comes from the change’s checks, read across every tracked prompt and engine the change was meant to move. These are the four words, with the text you see when you hover each one: How a change gets its word:
  • The latest check with a verdict decides. The +30-day check replaces the +14, which replaces the +7, which replaces the early +3, because a later window has more evidence. They are not averaged.
  • Moved up when more prompt-engine pairs were named more often than less often, past the significance test. Moved down is the reverse. When some pairs went the other way, the reason line says how many.
  • Nothing we can prove yet when no pair moved past the test, when pairs moved up and down in equal numbers, when there was too little measurement before the change to compare against, when the prompts it was meant to move are no longer tracked, when the change was never found on the live page, when its checks were stopped, when no tracked prompt is tied to it, or when no check is on record for it.
  • Too early while no check has a verdict and one is still booked or being read (the reason gives the date of the next booked one), and for delivered work that is not live yet, whose checks are booked once it is.
They appear on a question’s changes timeline, in its detail on the Scoreboard. There the verdict is about that question’s engines only.